Device, system, and method for gathering elements from memory

Abstract

A system and method for assigning values to elements in a first register, where each data field in a first register corresponds to a data element to be written into a second register, and where for each data field in the first register, a first value may indicate that the corresponding data element has not been written into the second register and a second value indicates that the corresponding data element has been written into the second register, reading the values of each of the data fields in the first register, and for each data field in the first register having the first value, gathering the corresponding data element and writing the corresponding data element into the second register, and changing the value of the data field in the first register from the first value to the second value. Other embodiments are described and claimed.

Description

BACKGROUND OF THE INVENTION[0001]Porting an application or software code may include changing the original source code of the application to make the application compile, install, and / or run on specific systems or architectures, such as for example, a wide or large width vector architecture. For such applications, memory access algorithms to the original source code, when ported to target code, may be complex, inconsistent, or noncontiguous, for example, as vector widths increase (e.g., for operations such as three dimensional (3D) image rendering). Memory used for processes, for example, run on a ported application may be stored in noncontiguous or non-adjacent memory locations.[0002]Mechanisms for improving memory access may include implementing gathering and scattering operations for generating local contiguous memory access for data from other non-local and / or noncontiguous memory locations. Gather operations may collect data from a set of noncontiguous or random memory location...

AI Technical Summary

Problems solved by technology

For such applications, memory access algorithms to the original source code, when ported to target code, may be complex, inconsistent, or noncontiguous, for example, as vector widths increase (e.g., for operations such as three dimensional (3D) image rendering).

If gather operations are interrupted, with some architectures, using ported code, the state of the machine may not be saved, requiring a repeat of the entire gather operation rather than a restart where the gather operation was interrupted.

Images